# Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2311.00523 · HTML: https://mlsanity.com/paper/2311.00523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 16 of 16)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Multi-Objective Counterfactual Explanations](https://mlsanity.com/paper/2004.11165/) (2020)
- [Learning Model-Agnostic Counterfactual Explanations for Tabular Data](https://mlsanity.com/paper/1910.09398/) (2019)
- [Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers](https://mlsanity.com/paper/1912.03277/) (2019)
- [Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)](https://mlsanity.com/paper/2005.13997/) (2020)
- [Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End](https://mlsanity.com/paper/2011.04917/) (2020)
- [NICE: An Algorithm for Nearest Instance Counterfactual Explanations](https://mlsanity.com/paper/2104.07411/) (2021)
- [Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space](https://mlsanity.com/paper/1810.06394/) (2018)
- [Counterfactual Explanations in Sequential Decision Making Under Uncertainty](https://mlsanity.com/paper/2107.02776/) (2021)
- [ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models](https://mlsanity.com/paper/2110.11960/) (2021)
- [Amortized Generation of Sequential Algorithmic Recourses for Black-box Models](https://mlsanity.com/paper/2106.03962/) (2021)
- [Synthesizing Action Sequences for Modifying Model Decisions](https://mlsanity.com/paper/1910.00057/) (2019)
- [Consequence-aware Sequential Counterfactual Generation](https://mlsanity.com/paper/2104.05592/) (2021)
- [XPROAX-Local explanations for text classification with progressive neighborhood approximation](https://mlsanity.com/paper/2109.15004/) (2021)

## Abstract (arXiv)

In the field of explainable Artificial Intelligence (XAI), sequential counterfactual (SCF) examples are often used to alter the decision of a trained classifier by implementing a sequence of modifications to the input instance. Although certain test-time algorithms aim to optimize for each new instance individually, recently Reinforcement Learning (RL) methods have been proposed that seek to learn policies for discovering SCFs, thereby enhancing scalability. As is typical in RL, the formulation of the RL problem, including the specification of state space, actions, and rewards, can often be ambiguous. In this work, we identify shortcomings in existing methods that can result in policies with undesired properties, such as a bias towards specific actions. We propose to use the output probabilities of the classifier to create a more informative reward, to mitigate this effect.